Commit 3f46c4e9 authored by Jonathan Kim's avatar Jonathan Kim Committed by Alex Deucher
Browse files

drm/amdkfd: report xgmi bandwidth between direct peers to the kfd 



Report the min/max bandwidth in megabytes to the kfd for direct
xgmi connections only.  Indirect peers will report 0 since
indirect route is unknown.

Signed-off-by: default avatarJonathan Kim <jonathan.kim@amd.com>
Reviewed-by: default avatarFelix Kuehling <felix.kuehling@amd.com>
Signed-off-by: default avatarAlex Deucher <alexander.deucher@amd.com>
parent 331e7818

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c

+24 −0
Original line number Diff line number Diff line
@@ -553,6 +553,30 @@ uint8_t amdgpu_amdkfd_get_xgmi_hops_count(struct kgd_dev *dst, struct kgd_dev *s 
	return  (uint8_t)ret;

}



int amdgpu_amdkfd_get_xgmi_bandwidth_mbytes(struct kgd_dev *dst, struct kgd_dev *src, bool is_min)

{

	struct amdgpu_device *adev = (struct amdgpu_device *)dst, *peer_adev;

	int num_links;



	if (adev->asic_type != CHIP_ALDEBARAN)

		return 0;



	if (src)

		peer_adev = (struct amdgpu_device *)src;



	/* num links returns 0 for indirect peers since indirect route is unknown. */

	num_links = is_min ? 1 : amdgpu_xgmi_get_num_links(adev, peer_adev);

	if (num_links < 0) {

		DRM_ERROR("amdgpu: failed to get xgmi num links between node %d and %d. ret = %d\n",

			adev->gmc.xgmi.physical_node_id,

			peer_adev->gmc.xgmi.physical_node_id, num_links);

		num_links = 0;

	}



	/* Aldebaran xGMI DPM is defeatured so assume x16 x 25Gbps for bandwidth. */

	return (num_links * 16 * 25000)/BITS_PER_BYTE;

}



uint64_t amdgpu_amdkfd_get_mmio_remap_phys_addr(struct kgd_dev *kgd)

{

	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h

+1 −0
Original line number Diff line number Diff line
@@ -226,6 +226,7 @@ uint32_t amdgpu_amdkfd_get_num_gws(struct kgd_dev *kgd); 
uint32_t amdgpu_amdkfd_get_asic_rev_id(struct kgd_dev *kgd);

int amdgpu_amdkfd_get_noretry(struct kgd_dev *kgd);

uint8_t amdgpu_amdkfd_get_xgmi_hops_count(struct kgd_dev *dst, struct kgd_dev *src);

int amdgpu_amdkfd_get_xgmi_bandwidth_mbytes(struct kgd_dev *dst, struct kgd_dev *src, bool is_min);



/* Read user wptr from a specified user address space with page fault

 * disabled. The memory must be pinned and mapped to the hardware when

drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c

+12 −0
Original line number Diff line number Diff line
@@ -486,6 +486,18 @@ int amdgpu_xgmi_get_hops_count(struct amdgpu_device *adev, 
	return	-EINVAL;

}



int amdgpu_xgmi_get_num_links(struct amdgpu_device *adev,

		struct amdgpu_device *peer_adev)

{

	struct psp_xgmi_topology_info *top = &adev->psp.xgmi_context.top_info;

	int i;



	for (i = 0 ; i < top->num_nodes; ++i)

		if (top->nodes[i].node_id == peer_adev->gmc.xgmi.node_id)

			return top->nodes[i].num_links;

	return	-EINVAL;

}



int amdgpu_xgmi_add_device(struct amdgpu_device *adev)

{

	struct psp_xgmi_topology_info *top_info;

drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h

+2 −0
Original line number Diff line number Diff line
@@ -59,6 +59,8 @@ int amdgpu_xgmi_remove_device(struct amdgpu_device *adev); 
int amdgpu_xgmi_set_pstate(struct amdgpu_device *adev, int pstate);

int amdgpu_xgmi_get_hops_count(struct amdgpu_device *adev,

		struct amdgpu_device *peer_adev);

int amdgpu_xgmi_get_num_links(struct amdgpu_device *adev,

		struct amdgpu_device *peer_adev);

uint64_t amdgpu_xgmi_get_relative_phy_addr(struct amdgpu_device *adev,

					   uint64_t addr);

static inline bool amdgpu_xgmi_same_hive(struct amdgpu_device *adev,

drivers/gpu/drm/amd/amdkfd/kfd_crat.c

+12 −0
Original line number Diff line number Diff line
@@ -1989,6 +1989,13 @@ static int kfd_fill_gpu_direct_io_link_to_cpu(int *avail_size, 
		sub_type_hdr->flags |= CRAT_IOLINK_FLAGS_BI_DIRECTIONAL;

		sub_type_hdr->io_interface_type = CRAT_IOLINK_TYPE_XGMI;

		sub_type_hdr->num_hops_xgmi = 1;

		if (adev->asic_type == CHIP_ALDEBARAN) {

			sub_type_hdr->minimum_bandwidth_mbs =

					amdgpu_amdkfd_get_xgmi_bandwidth_mbytes(

							kdev->kgd, NULL, true);

			sub_type_hdr->maximum_bandwidth_mbs =

					sub_type_hdr->minimum_bandwidth_mbs;

		}

	} else {

		sub_type_hdr->io_interface_type = CRAT_IOLINK_TYPE_PCIEXPRESS;

	}
@@ -2033,6 +2040,11 @@ static int kfd_fill_gpu_xgmi_link_to_gpu(int *avail_size, 
	sub_type_hdr->proximity_domain_to = proximity_domain_to;

	sub_type_hdr->num_hops_xgmi =

		amdgpu_amdkfd_get_xgmi_hops_count(kdev->kgd, peer_kdev->kgd);

	sub_type_hdr->maximum_bandwidth_mbs =

		amdgpu_amdkfd_get_xgmi_bandwidth_mbytes(kdev->kgd, peer_kdev->kgd, false);

	sub_type_hdr->minimum_bandwidth_mbs = sub_type_hdr->maximum_bandwidth_mbs ?

		amdgpu_amdkfd_get_xgmi_bandwidth_mbytes(kdev->kgd, NULL, true) : 0;



	return 0;

}